© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10717
    Prev
    Next
    INDEX
    Explanations

    change, transform, convert, or replace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vs
    -0.07
     Rid
    -0.06
    alen
    -0.06
     undis
    -0.06
    nam
    -0.06
    lut
    -0.06
    ewn
    -0.06
    ìķħ
    -0.06
    izi
    -0.06
     Jen
    -0.06
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.11
    åİŁæľ¬çļĦ
    0.10
    çİ°æľīçļĦ
    0.10
    åİŁæľī
    0.10
    åİŁæĿ¥çļĦ
    0.09
    å·²æľīçļĦ
    0.09
    èĬľ
    0.09
     existing
    0.08
    åİŁä¾Ĩ
    0.08
     기존ìĿĺ
    0.08
    Activations Density 0.224%

    No Known Activations